Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,267 Commits 274 Branches 239 Tags 397 MiB
40a7f47d22
Commit Graph

2267 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
David Burnett
ffa91be3f1 Install older version of torch and matching torchvision, fix pytorch-lightning=1.7.7 2022-11-02 14:49:36 -04:00
Lincoln Stein
2d5294bca1 speculative change for .bat installer 2022-11-02 13:56:17 -04:00
blessedcoolant
0453f21127 Fresh Build For WebUI 2022-11-02 23:26:49 +13:00
damian0815
9fc09aa4bd don't log base64 progress images 2022-11-02 22:32:31 +13:00
damian0815
2468a28e66 save VRAM by not recombining tensors that have been sliced to save VRAM 2022-11-01 22:39:48 -04:00
damian0815
e3ed748191 fix a bug that broke cross attention control index mapping 2022-11-01 22:39:39 -04:00
damian0815
3f5bf7ac44 report full size for fast latents and update conversion matrix for v1.5 2022-11-01 22:39:27 -04:00
damian0815
00378e1ea6 add damian0815 to contributors list 2022-11-01 22:38:16 -04:00
spezialspezial
5e87062cf8 Option to directly invert the grayscale heatmap - fix 2022-11-01 22:24:31 -04:00
spezialspezial
3e7a459990 Update txt2mask.py 2022-11-01 22:24:31 -04:00
spezialspezial
bbf4c03e50 Option to directly invert the grayscale heatmap 
Theoretically less work inverting the image while it's small but I can't measure a significant difference. Though, handy option to have in some cases.
 2022-11-01 22:24:31 -04:00
spezialspezial
b45e632f23 Option to directly invert the grayscale heatmap - fix 2022-11-01 22:18:00 -04:00
mauwii
611a3a9753 fix name of caching step 2022-11-01 22:17:23 -04:00
mauwii
1611f0d181 readd caching of sd-models 
- this would remove the necesarrity of the secret availability in PRs
 2022-11-01 22:17:23 -04:00
Lincoln Stein
08835115e4 pin pytorch_lightning to 1.7.7, issue #1331 2022-11-01 22:11:44 -04:00
Lincoln Stein
2d84e28d32 Merge branch 'development' of github.com:invoke-ai/InvokeAI into development 2022-11-01 22:11:04 -04:00
Lincoln Stein
57be9ae6c3 pin pytorch_lightning to 1.7.7, issue #1331 2022-11-01 22:10:12 -04:00
damian0815
ef17aae8ab add damian0815 to contributors list 2022-11-02 13:55:52 +13:00
damian0815
0cc39f01a3 report full size for fast latents and update conversion matrix for v1.5 2022-11-02 13:55:29 +13:00
damian0815
688d7258f1 fix a bug that broke cross attention control index mapping 2022-11-02 13:54:54 +13:00
damian0815
4513320bf1 save VRAM by not recombining tensors that have been sliced to save VRAM 2022-11-02 13:54:54 +13:00
spezialspezial
6c9a2761f5
Optional refined model for Txt2Mask 
Don't merge right now, just wanted to show the necessary changes
 2022-11-02 00:33:46 +01:00
Lincoln Stein
533fd04ef0 Merge branch 'development' of github.com:invoke-ai/InvokeAI into development 2022-11-01 17:40:36 -04:00
spezialspezial
2bdd738f03 Update txt2mask.py 2022-11-01 17:39:56 -04:00
spezialspezial
7782760541 Option to directly invert the grayscale heatmap 
Theoretically less work inverting the image while it's small but I can't measure a significant difference. Though, handy option to have in some cases.
 2022-11-01 17:39:56 -04:00
damian0815
dff5681cf0 shorter strings 2022-11-01 17:39:08 -04:00
damian0815
5a2790a69b convert progress display to a drop-down 2022-11-01 17:39:08 -04:00
damian0815
7c5305ccba do not try to save base64 intermediates in gallery on cancellation 2022-11-01 17:39:08 -04:00
psychedelicious
4013e8ad6f Fixes b64 image sending and displaying 2022-11-01 17:39:08 -04:00
damian
d1dfd257f9 wip base64 2022-11-01 17:39:08 -04:00
damian
5322d735ee update frontend 2022-11-01 17:39:08 -04:00
damian
cdb107dcda add option to show intermediate latent space 2022-11-01 17:39:08 -04:00
damian
be1393a41c ensure existing exception handling code also handles new exception class 2022-11-01 17:37:26 -04:00
Damian at mba
e554c2607f Rebuilt prompt parsing logic 
Complete re-write of the prompt parsing logic to be more readable and
logical, and therefore also hopefully easier to debug, maintain, and
augment.

In the process it has also become more robust to badly-formed prompts.

Squashed commit of the following:

commit 8fcfa88a16e1390d41717e940d72aed64712171c
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date:   Sun Oct 30 17:05:57 2022 +0100

    further cleanup

commit 1a1fd78bcfeb49d072e3e6d5808aa8df15441629
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date:   Sun Oct 30 16:07:57 2022 +0100

    cleanup and document

commit 099c9659fa8b8135876f9a5a50fe80b20bc0635c
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date:   Sun Oct 30 15:54:58 2022 +0100

    works fully

commit 5e6887ea8c25a1e21438ff6defb381fd027d25fd
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date:   Sun Oct 30 15:24:31 2022 +0100

    further...

commit 492fda120844d9bc1ad4ec7dd408a3374762d0ff
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date:   Sun Oct 30 14:08:57 2022 +0100

    getting there...

commit c6aab05a8450cc3c95c8691daf38fdc64c74f52d
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date:   Fri Oct 28 14:29:03 2022 +0200

    wip doesn't compile

commit 5e533f731cfd20cd435330eeb0012e5689e87e81
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date:   Fri Oct 28 13:21:43 2022 +0200

    working with CrossAttentionCtonrol but no Attention support yet

commit 9678348773431e500e110e8aede99086bb7b5955
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date:   Fri Oct 28 13:04:52 2022 +0200

    wip rebuiling prompt parser
 2022-11-01 17:37:26 -04:00
damian0815
de2686d323 fix crash (be a little less aggressive clearing out the attention slice) 2022-11-01 17:35:43 -04:00
damian0815
0b72a4a35e be more aggressive at clearing out saved_attn_slice 2022-11-01 17:35:34 -04:00
Lincoln Stein
6215592b12 Merge branch 'development' of github.com:invoke-ai/InvokeAI into development 2022-11-01 17:34:55 -04:00
damian0815
349cc25433 fix crash (be a little less aggressive clearing out the attention slice) 2022-11-01 17:34:28 -04:00
damian0815
214d276379 be more aggressive at clearing out saved_attn_slice 2022-11-01 17:34:28 -04:00
Lincoln Stein
ef24d76adc fix library problems in preload_modules 2022-11-01 17:23:27 -04:00
Lincoln Stein
ab2b5a691d fix model_cache memory management issues 2022-11-01 17:23:20 -04:00
Lincoln Stein
942a202945 fix model_cache memory management issues 2022-11-01 17:22:48 -04:00
Lincoln Stein
1379642fc6 fix library problems in preload_modules 2022-11-01 14:34:23 -04:00
Lincoln Stein
408cf5e092 candidate install scripts for testing 2022-11-01 13:54:42 -04:00
Lincoln Stein
ce298d32b5 attempt to make batch install more reliable 
1. added nvidia channel to environment.yml
2. updated pytorch-cuda requirement
3. let conda figure out what version of pytorch to install
4. add conda install status checking to .bat and .sh install files
5. in preload_models.py catch and handle download/access token errors
 2022-11-01 12:02:22 -04:00
mauwii
d7107d931a disable checks with sd-V1.4 model... 
...to save some resources, since V1.5 is the default now
 2022-10-31 21:35:33 -04:00
mauwii
147dcc2961 update test-invoke-conda.yml 
- fix model dl path for sd-v1-4.ckpt
- copy configs/models.yaml.example to configs/models.yaml
 2022-10-31 21:35:20 -04:00
mauwii
efd7f42414 fix models example weights for sd-v1.4 2022-10-31 21:35:09 -04:00
blessedcoolant
4e1b619ad7 [WebUI] Loopback Default False 2022-10-31 21:35:01 -04:00
mauwii
c7de2b2801 disable checks with sd-V1.4 model... 
...to save some resources, since V1.5 is the default now
 2022-10-31 21:19:53 -04:00